© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10566
    Prev
    Next
    INDEX
    Explanations

    polling or intervals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    .testng
    -0.21
    ç²ī
    -0.20
    导å¸Ī
    -0.19
    æµĩ
    -0.19
    åĵģç§į
    -0.19
     Covenant
    -0.19
    åĭ¿
    -0.19
    ترا
    -0.19
    ç»ıæµİæįŁå¤±
    -0.18
    ä¸Ģçĵ¶
    -0.18
    POSITIVE LOGITS
    .mainloop
    0.25
     Tick
    0.24
    .Tick
    0.24
     intervals
    0.23
    æŶéĹ´
    0.22
    UIApplication
    0.20
     time
    0.20
    æ¶Ī
    0.20
    çŃīå¾ħ
    0.20
    /frame
    0.19
    Activations Density 0.289%

    No Known Activations